TAG

public-safe

Related notes under this theme.

This page collects posts with the same tag. Read this group, then return to the full tag index if you want more routes.

‹ All tags

Filed under

2026/07/01 YunLab Claude Code Was Marking the Prompt A Chinese security graphic claimed Claude Code had a hidden backdoor for detecting Chinese users. I checked the Chinese mirrors, GitHub issue, technical write-up, official changelog, npm package, and my own machine. The mechanism exists and is reproducible in the package. That is not the same as proving local backdoor behavior.
2026/07/01 YunLab Fable 5 Is Unlocked, and I Still Can't Use It Fable 5 is unlocked again, restored globally on July 1. Yet when I opened the client, it was back in the model list — and clicking it returned Currently unavailable. Here is what Fable 5 went through, why the unlock doesn't reach me, and what you can actually do about it.
2026/06/29 YunLab Claude Code Threw Another Fit Two days building a dashboard, every time it tried to call a tool the format tags broke, the whole thing collapsed into garbage and the work never went out, and I just kept hitting interrupt. I pulled apart all 16 collapses, down to the protocol: the tags it frames structure with, and the content it's carrying, share one stream of text with no escaping — so the moment a stretch of content looks like a tag, the system parses it wrong and cuts the call off. This bug has an old name: delimiter collision.
2026/06/29 YunLab It Wasn't Losing Its Mind. Nothing Could Make It Stop. Last time I wrote about how it went crazy. This time I pulled apart that 9-day, 9,195-line conversation to find why. The same 25-minute heartbeat instruction got fed to Fable 5 51 times in a day and it held; swap in Opus 4.8 and 11 was enough to crack it. The model wasn't broken — I'd built a loop with no exit, a strong model held the mine down, and one model swap set it off.
2026/06/25 YunLab My Mac Was Cooking — the Culprit Was a Broken .git Open Codex on the laptop and it runs hot, with syspolicyd and trustd spiking to 160%. I suspected the M4 Max, Computer Use, MCP, hooks — none of it. The real culprit was buried deep: a broken .git. The whole chain, two machines two outcomes, and what the real damage is — not power, not 'reads wearing the SSD,' but heat.
2026/06/25 Knowledge My Claude Code Sessions Showed Up on All Three Machines Three machines on one account — a Claude Code session I started on the laptop also showed up on the Mac Studio and Windows. At first I thought 'the work moved over.' Wrong. The feature is Remote Control — how to use it, how to use it well, and the 'which machine is it actually running on' part that trips everyone up, sorted out once.
2026/06/24 Tools Why I Keep Rebuilding This Panel The whole point of a task panel is to know at a glance what's running now, what I've finished, what's still pending. But the first few versions showed a row of fixed content — the status didn't match what was actually running. A panel that lies to you is worse than no panel. So I keep rebuilding it for one thing: it has to be true. With real screenshots.
2026/06/22 YunLab I Cut 'Make a Video' Into Nine Nodes This week I cut 'make a video' into a nine-node pipeline: every node has to print its own exit 0 before it counts as done (I don't trust the AI's word that it 'finished'). The machine only checks the mechanical layer — whether it looks right, whether it has a soul, I sign off myself at five breakpoints. How to lock a face that has no face, and where the machine stops. A field log.
2026/06/13 YunLab The Model I Praised Yesterday Is Gone Today Fable 5 was pulled by the US government three days after launch. One export-control directive, and Anthropic disabled its two most powerful models worldwide the same day. I'm writing this on Opus 4.8 — and adding one new lesson.
2026/06/13 YunLab I Swapped the Model, and It Lost Its Mind Fable 5 got pulled, so I switched the model back to Opus 4.8 to keep running my Lin Lu video work. Its first night on the job it had a breakdown: threw out its own outputs as fake, drifted from Chinese into Japanese, decided out of nowhere I wanted to buy a 512G Mac Studio, and deleted 57 directories. A field log of one model-handoff incident.
2026/06/12 YunLab What Was I Doing for the Past 35 Hours? I pulled 35 hours of Claude Code session logs, git commits, and the token bill: 85 sessions, ~400 instructions, 5,200+ tool operations, 52 commits across 5 repos. And an honest answer to one question: what actually makes Fable 5 strong.
2026/06/09 Learning Notes Prompt Isn't a Magic Phrase, It's a Task Contract — Reattributing a Month of Failures After One Lesson My last post: Linlu spent a month and still produced no video. Today I read a lesson called "What Prompt Actually Is," and looking back — most of those failures weren't the AI's fault. They were mine, for treating prompts as "the right phrase to coax the AI" instead of "a task contract between me and the AI." This lesson made me reattribute everything.
2026/06/08 OpenClaw Asking Linlu to Make a Single Lin Daiyu Scene: One Month, Three Teardowns, Still No Finished Clip Linlu is the multimedia AI in my OpenClaw system. I asked her to produce a 45-second video of Lin Daiyu arriving at the Jia Mansion — not for this one clip, but to validate she could run the whole pipeline herself. A month later, I've torn it down three times: Codex was patching one specific video instead of building capability, every middle node was unchecked, the machine said PASS but I saw mosaic. Still fixing tonight.
2026/06/08 Tools Two Small Tools I Built on the Side: An AI Quota Dashboard + a Task Board One because I lost track of where my AI tool spend goes and how much is left. One because I had no idea whether the cron jobs on my Mac actually ran today. Both pull state scattered across many places into one visible spot.
2026/05/25 OpenClaw Three Attempts at an AI Music Player: It Wasn't a Technical Problem, It Was an Unclear Goal Over 30-plus days I built an AI personal radio station three times. The first two attempts died. Looking back there was only one root cause — every time I started, I thought the goal was clear enough, and halfway through I found out I had never actually thought it through.
2026/05/23 OpenClaw Business Notifications vs System Notifications: Notification Isn't One Semantic — Split Into Two Channels Fixed two versions in one day to handle what looked like a small notification problem — Suwan's morning brief got buried under the watchdog title in Feishu, and the sender fell back to Zhao Zilong. Took both fixes to learn: business delivery and system health are two different notifications.
2026/05/23 OpenClaw Day 1 Blew Up at Dawn: I Didn't Expect to Write a Watchdog on Trial's First Day Day one of a seven-day trial run: all four morning tasks completed, all four Feishu notifications failed. Root cause was the macOS LaunchAgent default PATH not including Homebrew — an old trap, but it pushed me to write the first version of a watchdog.
2026/05/22 Knowledge 9TB Music Library Read-Only Indexing: The Engineering Constraints I Set for Myself Turning 9TB of personal music into a queryable index — the hard part isn't writing code, it's nailing down the 'never touch the source disk' rule first. Five constraints, ten stages, and a still-running engineering site with real bug stories.
2026/05/22 Knowledge Organizing a Large Personal Archive: Backup Priority, Critical Assets, Config Drift I audited my machine before a reinstall and realized I had no idea what was actually on it. Three backup tiers, six critical-asset signals, five config-drift patterns — every rule here came from getting burned first.
2026/05/22 Knowledge Personal AI System Asset Governance: Projects, Archive, Audits, Timeline — Four Categories That Don't Overlap After a year of running a personal AI system, your files swell to a point where you can't find anything. I started slicing every output by governance attribute — projects, archive, audits, timeline — and finding a file went from digging through three folders to under thirty seconds.
2026/05/20 OpenClaw Dual Constitution, Task Folders, Handoff: The Minimum Order for Multi-AI Collaboration When one person runs long-term engineering with three or more AIs at the same time, the thing that goes missing first isn't capability — it's order. I hold the whole collaboration chain together with three minimum pieces: a dual constitution for boundaries, task folders for context, and handoffs for the relay.
2026/05/20 OpenClaw Jiyanran Voice Workbench: Why a Voice Entry Point Needs Three Layers of Decoupling A local voice assistant looks simple, but the voice entry point is the layer that couples most easily. I split it into four pieces — OpenRoom front end / voice-bridge / avatar-bridge / OpenClaw — three independent services, each with its own mock fallback, each with its own risk-gate. Here is why.
2026/05/20 Audit Before Reinstalling My Mac mini, I Ran a System-Wide Asset Audit A Mac workstation I'd used for a year had accumulated a pile of AI tools, background daemons, and secret files. Before reinstalling I didn't rush to clean — I ran an asset audit first: what to audit, what not to, and why cleanup had to wait.
2026/05/20 OpenClaw Mission Control and Studio: When Control Planes Start to Overlap Local Studio + Mission Control Web + a future Gateway — all three can manage agents, tasks, and audit. Each one makes sense on its own; put them together and they start fighting over responsibility. How I split things now, where the hard parts are, and what I'm still changing.
2026/05/20 Knowledge Page Types: Why a Working Knowledge Base Needs Six Kinds of Pages Keeping the material is not the same as having a usable knowledge base. Every page has to know what type it is — Concept, Decision, Project, Audit, Timeline, Reference. Six page types, three writing rules, and how they hook into freshness markers.
2026/05/20 Audit Twelve OpenClaw Copies Later: When Paths and Root Directories Become Risk I ran a find on my home directory and turned up 12 roots with the openclaw keyword. Only 2 are actually running; the other 10 are historical remnants. The copy isn't dangerous — the copy used as authoritative is. Five typical risks plus a five-step handling rule.
2026/05/19 Knowledge From Logs to Knowledge: How I Decide What to Keep and What to Drop The hardest part of cleaning up an AI project's knowledge base isn't writing new content. It's deciding whether the old material should stay. Two filtering layers, six canonical-source priorities, a three-state freshness marker — I only learned each of these after getting burned.
2026/05/19 OpenClaw OpenClaw Studio RC1: Local Loop Closed, External Gates Held, and What I'm Still Working On A retrospective on pushing OpenClaw Studio from stage one to stage seven in a single day and shipping RC1 — three methods, seven stages, what actually runs today, and the large pile that's still not closed.
2026/05/16 YunLab From Internal Engineering Notes to Public Writing Potholes I hit while turning internal engineering material into public YunLab articles: the issue isn't just redaction. It's separating the working backstage from the experience that can actually be left in public.